Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their performance is highly dependent on the prompting strategy and model scale. While reinforcement learning and fine-tuning have been deployed to boost reasoning, these approaches incur substantial computational and data overhead. In this work, we introduce Adaptive Graph of Thoughts (AGoT), a dynamic, graph-based inference framework that enhances LLM reasoning solely at test time. Rather than relying on fixed-step methods like Chain of Thought (CoT) or Tree of Thoughts (ToT), AGoT recursively decomposes complex queries into structured subproblems, forming an dynamic directed acyclic graph (DAG) of interdependent reasoning steps. By selectively expanding only those subproblems that require further analysis, AGoT unifies the strengths of chain, tree, and graph paradigms into a cohesive framework that allocates computation where it is most needed. We validate our approach on diverse benchmarks spanning multi-hop retrieval, scientific reasoning, and mathematical problem-solving, achieving up to 46.2% improvement on scientific reasoning tasks (GPQA) - comparable to gains achieved through computationally intensive reinforcement learning approaches and outperforming state-of-the-art iterative approaches. These results suggest that dynamic decomposition and structured recursion offer a scalable, cost-effective alternative to post-training modifications, paving the way for more robust, general-purpose reasoning in LLMs.

Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a conversational manner, human users can effectively influence an LLM to develop more thoughtful and accurate responses. Motivated by this insight, we propose the Iteration of Thought (IoT) framework for enhancing LLM responses by generating "thought"-provoking prompts vis a vis an input query and the current iteration of an LLM's response. Unlike static or semi-static approaches, e.g. Chain of Thought (CoT) or Tree of Thoughts (ToT), IoT adapts its reasoning path dynamically, based on evolving context, and without generating alternate explorative thoughts which are ultimately discarded. The three components of the IoT framework are (1) an Inner Dialogue Agent (IDA) responsible for generating instructive, context-specific prompts; (2) an LLM Agent (LLMA) that processes these prompts to refine its responses; and (3) an iterative prompting loop that implements a conversation between the former two components. We introduce two variants of our framework: Autonomous Iteration of Thought (AIoT), where an LLM decides when to stop iterating, and Guided Iteration of Thought (GIoT), which always forces a fixed number iterations. We investigate the performance of IoT across various datasets, spanning complex reasoning tasks from the GPQA dataset, explorative problem-solving in Game of 24, puzzle solving in Mini Crosswords, and multi-hop question answering from the HotpotQA dataset. Our results show that IoT represents a viable paradigm for autonomous response refinement in LLMs, showcasing significant improvements over CoT and thereby enabling more adaptive and efficient reasoning systems that minimize human intervention.

By integrating Artificial Intelligence (AI) with the Internet of Things (IoT), Artificial Intelligence of Things (AIoT) has revolutionized many fields. However, AIoT is facing the challenges of energy consumption and carbon emissions due to the continuous advancement of mobile technology. Fortunately, Generative AI (GAI) holds immense potential to reduce carbon emissions of AIoT due to its excellent reasoning and generation capabilities. In this article, we explore the potential of GAI for carbon emissions reduction and propose a novel GAI-enabled solution for low-carbon AIoT. Specifically, we first study the main impacts that cause carbon emissions in AIoT, and then introduce GAI techniques and their relations to carbon emissions. We then explore the application prospects of GAI in low-carbon AIoT, focusing on how GAI can reduce carbon emissions of network components. Subsequently, we propose a Large Language Model (LLM)-enabled carbon emission optimization framework, in which we design pluggable LLM and Retrieval Augmented Generation (RAG) modules to generate more accurate and reliable optimization problems. Furthermore, we utilize Generative Diffusion Models (GDMs) to identify optimal strategies for carbon emission reduction. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we insightfully provide open research directions for low-carbon AIoT.

Digital transformation is no longer an inward tactic used to reform an organisation's operations; it's now a necessary undertaking sought out by CIOs and IT leaders. Recent developments have pushed organisations to embrace digitisation, causing the fourth industrial revolution and technologies such as artificial intelligence to go mainstream. Even though, according to Gartner, only 53 per cent of AI projects make it from prototype into production, companies can't ignore the benefits of successful AI implementation. Enhanced AI solutions such as the artificial intelligence of things (AIoT), conversational AI and machine learning (ML) are improving the future of digital transformation and offer more innovative ways than ever before to address business challenges. Today's AI solutions can be customised to address a company's unique set of challenges.

The rapid growth of the Internet of Things (IoT) has been fuelled by the falling cost of sensors, the proliferation of connected devices, and the advancement of artificial intelligence (AI). The IoT is the network of physical objects (vehicles, devices, buildings, etc.) embedded with sensors, software, electronics, and network connectivity that allows these objects to collect and exchange data. According to a recent report from McKinsey, the IoT could have a total economic impact of up to $12.6 trillion per year by 2030. While the IoT is still in its infancy, the AIoT represents the next wave of the IoT, where AI is used to turn data into insights and actions. The AIoT has the potential to transform industries and society, and it is already starting to have an impact.

In recent years, the high complexity of the business environment, dynamism and environmental change, uncertainty and concepts such as globalization and increasing competition of organizations in the national and international arena have caused many changes in the equations governing the supply chain. In this case, supply chain organizations must always be prepared for a variety of challenges and dynamic environmental changes. One of the effective solutions to face these challenges is to create a resilient supply chain. Resilient supply chain is able to overcome uncertainties and disruptions in the business environment. The competitive advantage of this supply chain does not depend only on low costs, high quality, reduced latency and high level of service. Rather, it has the ability of the chain to avoid catastrophes and overcome critical situations, and this is the resilience of the supply chain. AI and IoT technologies and their combination, called AIoT, have played a key role in improving supply chain performance in recent years and can therefore increase supply chain resilience. For this reason, in this study, an attempt was made to better understand the impact of these technologies on equity by examining the dimensions and components of the Artificial Intelligence of Things (AIoT)-based supply chain. Finally, using nonlinear fuzzy decision making method, the most important components of the impact on the resilient smart supply chain are determined. Understanding this assessment can help empower the smart supply chain.

The Internet of Things, or IoT, plays a huge part in automating the world. IoT refers to how different devices are connected via the web and are able influence their surroundings. Now, these devices are increasingly starting to be able to make decisions by themselves. Driverless cars, self-operating factories and automatic health advice from fitness trackers are just three examples of how autonomous connected devices can transform society. The business implications of these innovations are huge.

IoT has seen steady adopted across the business world over the past decade. Businesses have been built or optimized using IoT devices and their data capabilities, ushering in a new era of business and consumer technology. Now the next wave is upon us as advances in AI and machine learning unleash the possibilities of IoT devices utilizing "artificial intelligence of things," or AIoT. Consumers, businesses, economies, and industries that adopt and invest in AIoT can leverage its power and gain competitive advantages. IoT collects the data, and AI analyzes it to simulate smart behavior and support decision-making processes with minimal human intervention.

The pandemic saw the birth of the (AIoT), an "artificial Internet of Things" technology ecosystem. The Smart Home was then created. The AIoT is a combination of connected things (the IoT) and artificial intelligence (the AI), which are used in these things. The past 12 months have been difficult. People now know that Covid-19 is here to stay after the pandemic.

Artificial intelligence has made its way into our daily lives, allowing organizations in a variety of industries to use it to improve marketing prospects and streamline operations. Every year, new advancements in artificial intelligence are produced that organizations may leverage in a variety of inventive ways. The year 2022 is expected to follow in the footsteps of its predecessors and leaders in a new era of artificial intelligence. The use of AI technology is being driven by a dynamic and competitive corporate climate, as well as customer interaction, to provide personalised services in real-time. Businesses in industries such as e-commerce, financial services, healthcare, and others are turning to artificial intelligence (AI) to improve consumer experience.